Arush Gadkar

Manycasting: Energy-Efficient Multicasting in WDM Optical Unicast Networks

With the increasing number of high-bandwidth applications, energy consumption of networks has become an important issue that needs to be addressed. Manycasting is a communication paradigm that finds applications in such high-bandwidth environments. To support manycasting functionality in an optical network that is Split-Incapable (SI), i.e., the optical cross connects are incapable of switching an incoming optical signal to more than one output interface, manycasting must be implemented as an overlay to the optical layer. We propose two such overlay approaches: Manycasting with Drop at Member Node (MA-DAMN) and Manycasting with Drop at Any Node (MA-DAAN) which employ Steiner tree routing. We subject these approaches to a static traffic model, and present integer linear programs (ILPs) and heuristic approximations which aim to minimize the total number of wavelengths required to service the manycast request set in an effort to reduce network-wide energy consumption. Through extensive simulation, we show that MA-DAMN and MA-DAAN achieve 25−45% wavelength reduction as compared to a baseline overlay approach which employs single-hop lightpaths to each manycast destination individually.

Dynamic circuit provisioning in all-optical WDM networks using lightpath switching ✩

Abstract In this paper we investigate the problem of provisioning holding-time-aware (HTA) dynamic circuits in all-optical wavelength division multiplexed (WDM) networks. We employ a technique called lightpath switching (LPS) wherein the data transmission may begin on one lightpath and switch to a different lightpath at a later time. Lightpath switches are transparent to the user and are managed by the network. Allowing LPS creates a number of segments that can use independent lightpaths. We first compare the performance of traditional routing and wavelength (RWA) assignment to routing and wavelength assignment with LPS. We show that LPS can significantly reduce blocking compared to traditional RWA. We then address the problem of routing dynamic anycast HTA dynamic circuits. We propose two heuristics to solve the anycast RWA problem: anycast with continuous segment (ACS) and anycast with lightpath switching (ALPS). In ALPS we exercise LPS, and provision a connection request by searching for the best candidate destination node is such a way that the network resources are utilized efficiently. In ACS we do not allow a connection request to switch lightpaths. The lightpaths to each candidate destination node of a request are computed using traditional RWA algorithms. We first compare the performance of ACS to ALPS and observe that ALPS achieves better blocking than ACS. Furthermore, we also compare the performance of these two anycast RWA algorithms to the traditional unicast RWA algorithm. We show that the anycast RWA algorithms presented here significantly outperform the traditional unicast RWA algorithms.

Dynamic Multicasting in WDM Optical Unicast Networks for Bandwidth-Intensive Applications

Traditionally in wavelength division multiplexed (WDM) networks, multicasting is accomplished by splitting the signals all-optically, thereby establishing a tree of lightpaths (light-tree) from the source to every destination. To provision for this functionality in a Multicast-Incapable environment, in which the switches are not capable of directing an incoming signal to more than one output interface, one must implement a logical multicast overlay to the underlying optical layer. A naive method of accomplishing this is by creating a set of unicast lightpaths from the source to each destination of the multicast request. However, for large multicast groups, this leads to a poor utilization of the network resources. To alleviate this problem, we present two multicast Steiner tree overlay alternatives: Multicast with Drop At Member Node (DAMN), in which a lightpath may only terminate at member nodes of the multicast request, and Multicast with Drop At Any Node (DAAN), in which lightpaths may terminate at any node in the physical topology. We consider a dynamic traffic model, and propose efficient heuristics to solve the DAMN and DAAN problems with a goal of minimizing the total number of wavelengths required to satisfy the request. Moreover, we present a simple heuristic to approximate the baseline unicast approach (naive method). Our results demonstrate that at various loads, both the DAMN and DAAN reduce wavelength consumption by 42 - 60% over the naive unicast approach in realistic networks.

Slotted advance reservation for multicast-incapable optical wavelength division multiplexing networks

In this paper we investigate techniques for provisioning advance reservation (AR) multicast requests in multicast-incapable (MI) networks, which lack the ability to split an incoming signal to multiple output ports, without performing an O-E-O conversion. AR traffic consists of connection requests that arrive and reserve network resources at some time before they need them to ensure better qualityof service than on-demand requests would receive. The traditional approach of providing multicast support in MI networks is to use an overlay approach in which a set of lightpaths is established from the source to each multicast destination member independently. This approach is wasteful of wavelength resources, particularly as the multicast destination set grows. We propose two alternative overlay approaches that take advantage of multiple-hop overlay-tree structures to limit the consumption of wavelengths in the network. We investigate static traffic scenarios on various network topologies and develop integer linear programs (ILPs) to optimally solve all three of the overlay-tree problems presented in this work with the goal of minimizing the total number of wavelengths required to service a multicast request set. We also present efficient heuristics that build and select overlay-trees that lower dynamic connection blocking and wavelength consumption. We compare the heuristics to the optimal ILPs on a small-scale network, and then further evaluate the heuristics on several large-scale topologies. In all scenarios, we are able to conclude that by sacrificing a minimization of O-E-O conversions, our more flexible overlay approaches, called drop at member node (MI-DMN) and dropatany node (MI-DAN), are superiorinterms of resource usage when compared with the traditional naive approach. Further dynamic traffic evaluations reveal that blocking may be lowered over the naive approach by more thantwoordersofmagnitudeatlowtomedium traffic loads.

Deadline-aware co-scheduling using anycast advance reservations in wavelength routed lambda grids

As grid applications evolve, the need for user controlled network infrastructure is apparent in order to support emerging dynamic and interactive services. Due to the inherent bandwidth offered by optical wavelength division multiplexed (WDM) networks, they prove to be a potential candidate to support the bandwidth intensive grid applications. In a grid environment, the available resources can be classified into two broad categories: grid resources which consist of computing and storage components that reside on each node of the network and network resources which provide bandwidth for the execution of a grid application. A typical grid application (job) is usually divided into a number of smaller tasks which need to be scheduled, on possibly different nodes of the network in order to ensure job completion. There usually exists some dependency between these tasks and a strict time-deadline within which the job needs to be completed. Rather than using an independent scheduling approach (at the grid and network levels), we address the co-scheduling problem in lambda-grids for advance reservation requests and aim at minimizing the job blocking probability. We use the anycasting communication paradigm referred to as co-anycasting, to allocate grid and network resources to all tasks of a job. We propose three heuristics: first free (FF), shortest hop (SH), and least used (LU) to solve the co-scheduling problem. Moreover, we compare the proposed co-anycasting approach to a grid-anycasting approach, wherein the anycasting flexibility is offered only at the grid level, and show through extensive simulations the performance benefit of using co-anycasting to support grid applications in a time-deadline environment.

Dynamic advance reservation multicast overlay for slotted optical WDM networks

In this paper we investigate techniques for provisioning advanced reservation multicast requests in Multicast-Incapable (MI) networks, which lack the ability to split an incoming signal to multiple output ports, without performing an O-E-O conversion. To implement the multicasting functionality in a MI network, we propose implementing it as a logical overlay to the optical layer. One such method is to reserve unicast lightpaths from the source node to each destination node of the multicast request. Referred to as Multicast Via WDM Unicast (MVWU), this solution tends to utilize the network resources in an inefficient manner. To address this problem we propose two novel overlay solutions: Drop At Member Node (DAMN) and Drop At Any Node (DAAN), wherein we create a set of lightpath routes (possibly multiple-hop) in the overlay layer to reach all the destinations of a multicast request. In DAMN, we allow a lightpath to terminate/originate only at nodes which belong to the set of destination nodes of the multicast request. DAAN relaxes this constraint and allows a lightpath to be terminated at any node in the network. We refer to the set of lightpath routes created in the overlay layer as overlay-trees. We consider dynamic traffic and present efficient heuristics to solve the MVWU, DAMN, and DAAN problems with a goal of minimizing the blocking probability of a request. Our results indicate that DAMN and DAAN outperform the MVWU approach. Further, we present different mechanisms to generate the overlay-trees and compare their relative performance on a real-world large-scale network.

Dynamic manycasting in optical split-incapable WDM networks for supporting high-bandwidth applications

With the advent of bandwidth intensive applications, the demand for manycast networking capabilities has become an essential component of wavelength division multiplexed (WDM) optical networks. Traditionally, the manycast functionality is accomplished by splitting a signal all-optically, thereby creating a light-tree, which originates from the source node and reaches a subset of the destination nodes. To support the manycasting functionality in an optical network that is split-incapable (SI), i.e., the optical crossconnects are incapable of switching an incoming optical signal to more than one output interface, one must implement a logical overlay to the underlying optical layer. A naiıve approach to accomplish this is by creating a set of unicast lightpaths that originate at the source node and terminate at a subset of the destination nodes of the manycast request. We refer to this as the manycasting via WDM unicast (MA-VWU) approach. However, for a large number of requests this approach leads to a poor utilization of network resources. To overcome this problem, we propose two overlay approaches: manycasting with drop at member node (MA-DAMN) and manycasting with drop at any node (MA-DAAN). In these solutions, we achieve manycasting by creating a set of lightpath routes (possibly multiple hops) in the overlay layer. We consider a dynamic traffic model and propose efficient heuristics to solve the MA-DAMN and MA-DAAN problems with a goal of minimizing the total number of wavelengths required to satisfy the requests. Our results demonstrate that both the overlay approaches reduce the wavelength consumption by approximately 33-45% over the MA-VWU approach for real-world large-scale networks1.

Dynamic anycasting over wavelength routed networks with lightpath switching

In this paper we investigate the problem of provisioning dynamic anycast holding-time-aware (HTA) lightpaths in all-optical wavelength division multiplexed (WDM) networks. We employ a technique called lightpath switching (LPS) wherein the data transmission may begin on one lightpath and switch to a different lightpath at a later time. We propose two heuristics to solve the anycast routing and wavelength assignment (RWA) problem: anycast with continuous segment (ACS) and anycast with lightpath switching (ALPS). We first compare the performance of ACS to ALPS and observe that ALPS achieves better blocking than ACS. Furthermore, we also compare the performance of these two anycast RWA algorithms to the traditional unicast RWA algorithm. We show that the anycast RWA algorithms presented here significantly out-perform the traditional unicast RWA algorithms.

Manycast overlay in split-incapable networks for supporting bandwidth-intensive applications

Recent trends in science applications call for long-range and large-scale collaboration among laboratories and super-computing sites. Long gone are the days of entering data manually into a spreadsheet on a local workstation. The worlds most powerful and ground-breaking experiments generate exabytes of information, which must be distributed to multiple labs for analysis and interpretation. Such trends reveal the unwavering importance of new communication paradigms, like multicasting and manycasting, which provide point-to-multipoint data transfers. Typically, these all-important mechanisms are provided at the optical layer, where split-capable cross-connects split input signals into multiple output signals all-optically. Unfortunately, some of the worlds largest and most powerful networks do not have the hardware infrastructure to support such functionality, but allow for point-to-point communication exclusively. In such split-incapable (SI) networks, multicast and manycast must be provided as a logical overlay to the pre-existing and limited unicast infrastructure. In this paper, we present two overlay models for providing manycast support in SI networks: Manycasting with Drop at Member Node (MA-DMN) and Manycasting with Drop at Any Node (MA-DAN). Through the development of integer linear programs (ILPs) and heuristics, we evaluate these models in terms of both optimal solutions and efficient approximations for both small-scale and large-scale networks and consider both static and dynamic traffic scenarios. Our results demonstrate that despite a small tradeoff in additional complexity and delay from signal conversion to the optical domain, our models provide efficient utilization of network resources and greatly surpass the standard naive approach of establishing paths to every destination.

Static manycast advance reservation in split-incapable optical networks

Recent explosion of high-bandwidth applications and scientific collaboration has expedited the need for scheduled transmission of data to multiple scientific sites around the world. Advance reservations (AR) promote efficient bandwidth utilization, particularly when demands are high. The collaborative nature of modern science calls for more flexible point-to-multipoint distribution paradigms, such as manycasting. Combining AR and manycast communication mechanisms enables intelligent resource utilization in optical networks to support future e-science applications. Limiting the adoption of point-to-multipoint communication is the physical handicap that many optical crossconnects are Split-Incapable (SI), i.e., all-optical splitting of signals is not supported, making optical AR manycasting infeasible. In this paper, we adapt solutions which have previously only been considered in immediate reservation (IR) scenarios to provide manycasting as a multi-hop logical overlay to the unicast-only optical layer. We develop ILPs and heuristics to evaluate the resource consumption for various AR traffic scenarios 1.